mlsanityData to 14 Oct 2026

CoMI-IRL: Contrastive Multi-Intention Inverse Reinforcement Learning

arXiv 2602.07496 ↗First posted 7 Feb 2026cs.LGcited by 2

On the map: Offline RL and imitation learning from data → Inverse reinforcement learning

also in 1 more
Abstract (arXiv)

Inverse Reinforcement Learning (IRL) seeks to infer reward functions from expert demonstrations. When demonstrations originate from multiple experts with different intentions, the problem is known as Multi-Intention IRL (MI-IRL). Recent deep generative MI-IRL approaches couple behavior clustering and reward learning, but typically require prior knowledge of the number of true behavioral modes K^*. This reliance on expert knowledge limits their adaptability to new behaviors, and only enables analysis related to the learned rewards, and not across the behavior modes used to train them. We propose Contrastive Multi-Intention IRL (CoMI-IRL), a transformer-based unsupervised framework that decouples behavior representation and clustering from downstream reward learning. Our experiments show that CoMI-IRL outperforms existing approaches without a priori knowledge of K^* or labels, while allowing for visual interpretation of behavior relationships and adaptation to unseen behavior without full retraining.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in Inverse reinforcement learning, one of 13 directions in Offline RL and imitation learning from data. Builds on 31 of its 61 references that are in the map. First posted on arXiv 7 Feb 2026.

Builds on

31 of 61 references.

Closest ancestors · 2

Same direction, newest first

  1. 2021Deep Adaptive Multi-Intention Inverse Reinforcement Learning14 Jul
  2. 2021LiMIIRL: Lightweight Multiple-Intent Inverse Reinforcement Learning3 Jun

Other references · 29

  1. 2017Attention Is All You Needcited by 60,361
  2. 2018BERT: Pre-training of Deep Bidirectional Transformers for Language Understandingcited by 40,399
  3. 2020A Simple Framework for Contrastive Learning of Visual Representationscited by 12,049
  4. 2018Representation Learning with Contrastive Predictive Codingcited by 7,777
  5. 2018UMAP: Uniform Manifold Approximation and Projection for Dimension Reductioncited by 2,898
  6. 2020Fourier Features Let Networks Learn High Frequency Functions in Low Dimensional Domainscited by 2,200
  7. 2021SimCSE: Simple Contrastive Learning of Sentence Embeddingscited by 2,173
  8. 2016Generative Adversarial Imitation Learningcited by 1,597
  9. 2021Decision Transformer: Reinforcement Learning via Sequence Modelingcited by 1,546
  10. 2020Understanding Contrastive Representation Learning through Alignment and Uniformity on the Hyperspherecited by 1,405
  11. 2018On the Spectral Bias of Neural Networkscited by 1,341
  12. 2018Learning deep representations by mutual information estimation and maximizationcited by 1,273
17 more
  1. 2017Learning Robust Rewards with Adversarial Inverse Reinforcement Learningcited by 490
  2. 2018From Louvain to Leiden: guaranteeing well-connected communitiescited by 385
  3. 2016A Connection between Generative Adversarial Networks, Inverse Reinforcement Learning, and Energy-Based Modelscited by 168
  4. 2023Representational Strengths and Limitations of Transformerscited by 133
  5. 2021Learnable Fourier Features for Multi-Dimensional Spatial Positional Encodingcited by 93
  6. 2017Multi-Modal Imitation Learning from Unstructured Demonstrations using Generative Adversarial Netscited by 64
  7. 2019Self-attention with Functional Time Representation Learningcited by 52
  8. 2022Contrastive Trajectory Similarity Learning with Dual-Feature Attentioncited by 44
  9. 2024[CLS] Token Tells Everything Needed for Training-free Efficient MLLMscited by 26
  10. 2022The NLP Task Effectiveness of Long-Range Transformerscited by 22
  11. 2022Learning Options via Compressioncited by 22
  12. 2022Trading Positional Complexity vs. Deepness in Coordinate Networkscited by 16
  13. 2022Strongly Augmented Contrastive Clusteringcited by 14
  14. 2017Inverse Reinforce Learning with Nonparametric Behavior Clusteringcited by 4
  15. 2025On Learning Informative Trajectory Embeddings for Imitation, Classification and Regressioncited by 3
  16. 2025Contrast & Compress: Learning Lightweight Embeddings for Short Trajectoriescited by 3
  17. 2025Discrete Contrastive Learning for Diffusion Policies in Autonomous Drivingcited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026ConTraIRL: Factorized Contrastive Abstractions for Transferable IRLcited by 0
  2. 2026Objective-Behavior Alignment: Diagnostics for MORL Policy Selectioncited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Generalize and Guide: Decomposing Rewards for Few-Shot Inverse Reinforcement Learning
  2. 2022Basis for Intentions: Efficient Inverse Reinforcement Learning using Past Experience
  3. 2023Multi-intention Inverse Q-learning for Interpretable Behavior Representation
  4. 2025Generalizing Behavior via Inverse Reinforcement Learning with Closed-Form Reward Centroids
  5. 2019CWAE-IRL: Formulating a supervised approach to Inverse Reinforcement Learning problem
  6. 2022Context-Hierarchy Inverse Reinforcement Learning
  7. 2019Meta-Inverse Reinforcement Learning with Probabilistic Context Variables
  8. 2018A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress